{"id":"W2964315724","doi":"10.48550/arxiv.1605.08988","title":"On Explore-Then-Commit Strategies","year":2016,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":59,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Commit; Minimax; Mathematical optimization; Asymptotically optimal algorithm; Simple (philosophy); Gaussian; Computer science; Order (exchange); Time horizon; Empirical evidence; Horizon; Mathematical economics; Mathematics; Economics; Machine learning","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005306371,0.002034727,0.002228245,0.0008652667,0.0007143329,0.002322169,0.001875162,0.003043824,0.005952096],"category_scores_gemma":[0.03012438,0.0007913276,0.0008671416,0.001229445,0.002662672,0.003597163,0.002056234,0.003664624,0.0009548941],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001993087,"about_ca_system_score_gemma":0.001967602,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002494968,"about_ca_topic_score_gemma":0.001610584,"domain_scores_codex":[0.9969211,0.001784322,0.0001188599,0.0004298641,0.0003680033,0.0003779364],"domain_scores_gemma":[0.9776837,0.01907209,0.001365751,0.0006212232,0.0006267966,0.0006304365],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004704898,0.0001794254,0.001534613,0.0002912633,0.0001449363,0.0002405366,0.0003088309,0.6108882,0.001253225,0.3562648,0.002804756,0.02561899],"study_design_scores_gemma":[0.0000868604,0.0001536206,0.0002063315,0.00006326687,0.00002385856,0.00004521173,0.00004259743,0.8230346,0.0003693431,0.1749098,0.0010441,0.0000202923],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09339536,0.002078403,0.8740434,0.002984012,0.0001519063,0.0002267457,0.000286347,0.0002800411,0.02655386],"genre_scores_gemma":[0.8967816,0.001492861,0.08550455,0.0008178829,0.0002002976,0.0005284835,0.0002314148,0.0001961929,0.01424662],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005952096,"threshold_uncertainty_score":0.02806312,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3686539785191696,"score_gpt":0.3317025144979235,"score_spread":0.03695146402124605,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}